| { | |
| "best_metric": 1.3130438327789307, | |
| "best_model_checkpoint": "miner_id_24/checkpoint-50", | |
| "epoch": 1.1541218637992832, | |
| "eval_steps": 25, | |
| "global_step": 50, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.022939068100358423, | |
| "grad_norm": 262.8689880371094, | |
| "learning_rate": 3.3333333333333335e-05, | |
| "loss": 66.2981, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.022939068100358423, | |
| "eval_loss": 2.5055336952209473, | |
| "eval_runtime": 4.7241, | |
| "eval_samples_per_second": 10.584, | |
| "eval_steps_per_second": 2.752, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.045878136200716846, | |
| "grad_norm": 341.7585754394531, | |
| "learning_rate": 6.666666666666667e-05, | |
| "loss": 68.6937, | |
| "step": 2 | |
| }, | |
| { | |
| "epoch": 0.06881720430107527, | |
| "grad_norm": 207.7501220703125, | |
| "learning_rate": 0.0001, | |
| "loss": 59.574, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 0.09175627240143369, | |
| "grad_norm": 110.24981689453125, | |
| "learning_rate": 9.997376600647783e-05, | |
| "loss": 54.2645, | |
| "step": 4 | |
| }, | |
| { | |
| "epoch": 0.11469534050179211, | |
| "grad_norm": 99.47808074951172, | |
| "learning_rate": 9.989509461357426e-05, | |
| "loss": 54.3133, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 0.13763440860215054, | |
| "grad_norm": 92.41586303710938, | |
| "learning_rate": 9.976407754861426e-05, | |
| "loss": 52.4341, | |
| "step": 6 | |
| }, | |
| { | |
| "epoch": 0.16057347670250896, | |
| "grad_norm": 78.24821472167969, | |
| "learning_rate": 9.958086757163489e-05, | |
| "loss": 52.4227, | |
| "step": 7 | |
| }, | |
| { | |
| "epoch": 0.18351254480286738, | |
| "grad_norm": 78.63040161132812, | |
| "learning_rate": 9.934567829727386e-05, | |
| "loss": 47.8582, | |
| "step": 8 | |
| }, | |
| { | |
| "epoch": 0.2064516129032258, | |
| "grad_norm": 85.06551361083984, | |
| "learning_rate": 9.905878394570453e-05, | |
| "loss": 47.9548, | |
| "step": 9 | |
| }, | |
| { | |
| "epoch": 0.22939068100358423, | |
| "grad_norm": 95.92952728271484, | |
| "learning_rate": 9.872051902290737e-05, | |
| "loss": 46.4105, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.2523297491039427, | |
| "grad_norm": 76.65313720703125, | |
| "learning_rate": 9.833127793065098e-05, | |
| "loss": 41.4597, | |
| "step": 11 | |
| }, | |
| { | |
| "epoch": 0.2752688172043011, | |
| "grad_norm": 71.17744445800781, | |
| "learning_rate": 9.789151450663723e-05, | |
| "loss": 50.646, | |
| "step": 12 | |
| }, | |
| { | |
| "epoch": 0.2982078853046595, | |
| "grad_norm": 60.47771453857422, | |
| "learning_rate": 9.740174149534693e-05, | |
| "loss": 48.6955, | |
| "step": 13 | |
| }, | |
| { | |
| "epoch": 0.3211469534050179, | |
| "grad_norm": 62.11365509033203, | |
| "learning_rate": 9.686252995020249e-05, | |
| "loss": 49.3354, | |
| "step": 14 | |
| }, | |
| { | |
| "epoch": 0.34408602150537637, | |
| "grad_norm": 57.970787048339844, | |
| "learning_rate": 9.627450856774539e-05, | |
| "loss": 47.0324, | |
| "step": 15 | |
| }, | |
| { | |
| "epoch": 0.36702508960573477, | |
| "grad_norm": 67.41333770751953, | |
| "learning_rate": 9.563836295460398e-05, | |
| "loss": 45.6518, | |
| "step": 16 | |
| }, | |
| { | |
| "epoch": 0.3899641577060932, | |
| "grad_norm": 66.67488861083984, | |
| "learning_rate": 9.495483482810688e-05, | |
| "loss": 47.9687, | |
| "step": 17 | |
| }, | |
| { | |
| "epoch": 0.4129032258064516, | |
| "grad_norm": 64.26166534423828, | |
| "learning_rate": 9.422472115147382e-05, | |
| "loss": 44.4571, | |
| "step": 18 | |
| }, | |
| { | |
| "epoch": 0.43584229390681006, | |
| "grad_norm": 65.23554229736328, | |
| "learning_rate": 9.3448873204592e-05, | |
| "loss": 46.1585, | |
| "step": 19 | |
| }, | |
| { | |
| "epoch": 0.45878136200716846, | |
| "grad_norm": 71.3513412475586, | |
| "learning_rate": 9.2628195591462e-05, | |
| "loss": 46.1975, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.4817204301075269, | |
| "grad_norm": 69.01107025146484, | |
| "learning_rate": 9.176364518546989e-05, | |
| "loss": 43.0764, | |
| "step": 21 | |
| }, | |
| { | |
| "epoch": 0.5046594982078854, | |
| "grad_norm": 62.19290542602539, | |
| "learning_rate": 9.08562300137157e-05, | |
| "loss": 43.0619, | |
| "step": 22 | |
| }, | |
| { | |
| "epoch": 0.5275985663082438, | |
| "grad_norm": 53.53089904785156, | |
| "learning_rate": 8.990700808169889e-05, | |
| "loss": 47.629, | |
| "step": 23 | |
| }, | |
| { | |
| "epoch": 0.5505376344086022, | |
| "grad_norm": 50.920841217041016, | |
| "learning_rate": 8.891708613973126e-05, | |
| "loss": 46.6122, | |
| "step": 24 | |
| }, | |
| { | |
| "epoch": 0.5734767025089605, | |
| "grad_norm": 60.60609436035156, | |
| "learning_rate": 8.788761839251559e-05, | |
| "loss": 49.2598, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 0.5734767025089605, | |
| "eval_loss": 1.374174952507019, | |
| "eval_runtime": 4.8014, | |
| "eval_samples_per_second": 10.414, | |
| "eval_steps_per_second": 2.708, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 0.596415770609319, | |
| "grad_norm": 58.53727722167969, | |
| "learning_rate": 8.681980515339464e-05, | |
| "loss": 46.5847, | |
| "step": 26 | |
| }, | |
| { | |
| "epoch": 0.6193548387096774, | |
| "grad_norm": 55.56049346923828, | |
| "learning_rate": 8.571489144483944e-05, | |
| "loss": 45.1878, | |
| "step": 27 | |
| }, | |
| { | |
| "epoch": 0.6422939068100358, | |
| "grad_norm": 63.621734619140625, | |
| "learning_rate": 8.457416554680877e-05, | |
| "loss": 46.4274, | |
| "step": 28 | |
| }, | |
| { | |
| "epoch": 0.6652329749103942, | |
| "grad_norm": 61.650733947753906, | |
| "learning_rate": 8.339895749467238e-05, | |
| "loss": 42.2788, | |
| "step": 29 | |
| }, | |
| { | |
| "epoch": 0.6881720430107527, | |
| "grad_norm": 59.424530029296875, | |
| "learning_rate": 8.219063752844926e-05, | |
| "loss": 42.7856, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 0.7111111111111111, | |
| "grad_norm": 65.62605285644531, | |
| "learning_rate": 8.095061449516903e-05, | |
| "loss": 45.3296, | |
| "step": 31 | |
| }, | |
| { | |
| "epoch": 0.7340501792114695, | |
| "grad_norm": 62.037506103515625, | |
| "learning_rate": 7.968033420621935e-05, | |
| "loss": 38.7791, | |
| "step": 32 | |
| }, | |
| { | |
| "epoch": 0.7569892473118279, | |
| "grad_norm": 54.389366149902344, | |
| "learning_rate": 7.838127775159452e-05, | |
| "loss": 43.6419, | |
| "step": 33 | |
| }, | |
| { | |
| "epoch": 0.7799283154121864, | |
| "grad_norm": 48.2963981628418, | |
| "learning_rate": 7.705495977301078e-05, | |
| "loss": 47.0971, | |
| "step": 34 | |
| }, | |
| { | |
| "epoch": 0.8028673835125448, | |
| "grad_norm": 47.147064208984375, | |
| "learning_rate": 7.570292669790186e-05, | |
| "loss": 43.7131, | |
| "step": 35 | |
| }, | |
| { | |
| "epoch": 0.8258064516129032, | |
| "grad_norm": 49.53687286376953, | |
| "learning_rate": 7.43267549363537e-05, | |
| "loss": 44.4156, | |
| "step": 36 | |
| }, | |
| { | |
| "epoch": 0.8487455197132616, | |
| "grad_norm": 47.156898498535156, | |
| "learning_rate": 7.292804904308087e-05, | |
| "loss": 39.8579, | |
| "step": 37 | |
| }, | |
| { | |
| "epoch": 0.8716845878136201, | |
| "grad_norm": 49.07862854003906, | |
| "learning_rate": 7.150843984658754e-05, | |
| "loss": 42.7801, | |
| "step": 38 | |
| }, | |
| { | |
| "epoch": 0.8946236559139785, | |
| "grad_norm": 54.775672912597656, | |
| "learning_rate": 7.006958254769438e-05, | |
| "loss": 43.8881, | |
| "step": 39 | |
| }, | |
| { | |
| "epoch": 0.9175627240143369, | |
| "grad_norm": 53.687408447265625, | |
| "learning_rate": 6.861315478964841e-05, | |
| "loss": 40.9659, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 0.9405017921146953, | |
| "grad_norm": 62.848514556884766, | |
| "learning_rate": 6.714085470206609e-05, | |
| "loss": 42.5454, | |
| "step": 41 | |
| }, | |
| { | |
| "epoch": 0.9634408602150538, | |
| "grad_norm": 62.29214096069336, | |
| "learning_rate": 6.56543989209901e-05, | |
| "loss": 39.6969, | |
| "step": 42 | |
| }, | |
| { | |
| "epoch": 0.9863799283154122, | |
| "grad_norm": 70.89318084716797, | |
| "learning_rate": 6.415552058736854e-05, | |
| "loss": 40.2985, | |
| "step": 43 | |
| }, | |
| { | |
| "epoch": 1.0164874551971326, | |
| "grad_norm": 46.05546188354492, | |
| "learning_rate": 6.264596732629e-05, | |
| "loss": 40.5047, | |
| "step": 44 | |
| }, | |
| { | |
| "epoch": 1.039426523297491, | |
| "grad_norm": 55.51439666748047, | |
| "learning_rate": 6.112749920933111e-05, | |
| "loss": 38.4444, | |
| "step": 45 | |
| }, | |
| { | |
| "epoch": 1.0623655913978494, | |
| "grad_norm": 42.752933502197266, | |
| "learning_rate": 5.960188670239154e-05, | |
| "loss": 36.3928, | |
| "step": 46 | |
| }, | |
| { | |
| "epoch": 1.0853046594982079, | |
| "grad_norm": 44.83907699584961, | |
| "learning_rate": 5.80709086014102e-05, | |
| "loss": 38.2118, | |
| "step": 47 | |
| }, | |
| { | |
| "epoch": 1.1082437275985664, | |
| "grad_norm": 48.16358184814453, | |
| "learning_rate": 5.653634995836856e-05, | |
| "loss": 33.5141, | |
| "step": 48 | |
| }, | |
| { | |
| "epoch": 1.1311827956989247, | |
| "grad_norm": 45.349609375, | |
| "learning_rate": 5.500000000000001e-05, | |
| "loss": 31.2986, | |
| "step": 49 | |
| }, | |
| { | |
| "epoch": 1.1541218637992832, | |
| "grad_norm": 46.83755874633789, | |
| "learning_rate": 5.346365004163145e-05, | |
| "loss": 33.2819, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 1.1541218637992832, | |
| "eval_loss": 1.3130438327789307, | |
| "eval_runtime": 4.775, | |
| "eval_samples_per_second": 10.471, | |
| "eval_steps_per_second": 2.723, | |
| "step": 50 | |
| } | |
| ], | |
| "logging_steps": 1, | |
| "max_steps": 95, | |
| "num_input_tokens_seen": 0, | |
| "num_train_epochs": 3, | |
| "save_steps": 25, | |
| "stateful_callbacks": { | |
| "EarlyStoppingCallback": { | |
| "args": { | |
| "early_stopping_patience": 1, | |
| "early_stopping_threshold": 0.0 | |
| }, | |
| "attributes": { | |
| "early_stopping_patience_counter": 0 | |
| } | |
| }, | |
| "TrainerControl": { | |
| "args": { | |
| "should_epoch_stop": false, | |
| "should_evaluate": false, | |
| "should_log": false, | |
| "should_save": true, | |
| "should_training_stop": false | |
| }, | |
| "attributes": {} | |
| } | |
| }, | |
| "total_flos": 5.658021338284032e+17, | |
| "train_batch_size": 1, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |